British researchers have developed a new AI-based algorithm that may one day help doctors quickly diagnose heart attacks
Posted Date – Fri, 5/12/23 at 11:15pm
London: British researchers have developed a new artificial intelligence (AI)-based algorithm that may one day help doctors quickly and accurately diagnose heart attacks.
According to researchers at the University of Edinburgh, the new algorithm, called CoDE-ACS, was able to rule out heart attacks in more than twice as many patients, with an accuracy of 99.6 per cent compared with current testing methods.
CoDE-ACS can also greatly help reduce hospitalization rates and quickly identify patients who can go home safely. The findings were published in the journal Nature Medicine.
“For patients with acute chest pain from a heart attack, early diagnosis and treatment can save lives,” said Professor Nicholas Mills, who led the research.
“Unfortunately, many conditions can cause these common symptoms, and diagnosis is not always simple.
“Using data and artificial intelligence to support clinical decision-making has enormous potential to improve patient care and efficiency in our busy emergency departments,” Mills noted.
In addition to ruling out a heart attack, CoDE-ACS can also help doctors identify those abnormal levels of troponin (a protein released into the blood during a heart attack) that are caused by the heart attack rather than another disorder.
“Chest pain is one of the most common reasons people visit emergency departments,” said Professor Nilesh Samani, Medical Director at the British Heart Foundation.
“Every day, physicians around the world are challenged to separate patients whose pain is due to a heart attack from those whose pain is due to a less severe condition,” he added.
CoDE-ACS was developed using data from 10,038 Scottish patients admitted to hospital with a suspected heart attack.
It uses routinely collected patient information, such as age, gender, EKG results and medical history, and troponin levels, to predict a person’s likelihood of having a heart attack.
The result is a probability score from 0 to 100 for each patient.
A clinical trial is currently underway in Scotland to assess whether the tool can help doctors reduce the pressure on overcrowded emergency rooms.
